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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18831
    Prev
    Next
    INDEX
    Explanations

    ih

    np_max-act-logits · gemini-2.0-flash
    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
     tương
    -0.09
    ATIONS
    -0.09
     Mere
    -0.09
    ல்கள்
    -0.08
     WARRANTIES
    -0.08
     Matching
    -0.08
     sở
    -0.08
    ctions
    -0.08
     þur
    -0.08
     Helping
    -0.08
    POSITIVE LOGITS
    ுள்ளதாக
    0.11
    fähig
    0.11
    ier
    0.11
    il
    0.10
    istically
    0.10
     للغاية
    0.10
    -minded
    0.09
    ably
    0.09
    teous
    0.09
    quicklich
    0.09
    Activations Density 0.123%

    No Known Activations