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. 23-RESID-POST-AA
    6. 130767
    Prev
    Next
    INDEX
    Explanations

    of

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -To
    -0.09
    .:
    -0.09
    -B
    -0.08
    -The
    -0.08
    -Col
    -0.08
    -And
    -0.08
     wied
    -0.08
    -sizing
    -0.08
    -J
    -0.08
    -All
    -0.08
    POSITIVE LOGITS
     occurrences
    0.13
     способов
    0.13
     deaths
    0.12
     servings
    0.11
     gånger
    0.11
     ಬಾರಿ
    0.11
     distinct
    0.11
     façons
    0.11
     مرات
    0.11
     fatalities
    0.11
    Activations Density 0.120%

    No Known Activations