Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 2
    Prev
    Next
    INDEX
    Explanations

    humane and deep topics

    np_max-act-logits · gemini-2.0-flash

    inspiration Method used: 2, Reason: Texts consistently discuss uplifting, forward-looking themes about human potential and meaning

    np_max-act · claude-3-5-haiku-20241022Triggered by @kdearsty
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veggies
    -0.09
     your
    -0.08
     helps
    -0.08
    !,
    -0.08
    ![
    -0.08
    !↵
    -0.08
     hehe
    -0.08
     divertido
    -0.08
    !↵↵
    -0.08
     accessories
    -0.08
    POSITIVE LOGITS
     sanctuary
    0.10
     twilight
    0.10
     existência
    0.10
     എന്നാല്
    0.09
     existir
    0.09
    ’existence
    0.09
     communion
    0.09
     פֿאַר
    0.09
     שינוי
    0.09
    ㆍ
    0.09
    Activations Density 0.059%

    No Known Activations