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. 11-RESID-POST-AA
    6. 41982
    Prev
    Next
    INDEX
    Explanations

    Mixed sources and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fruity
    -0.08
     সন্তান
    -0.08
    Fruit
    -0.07
    cı
    -0.07
     çocuk
    -0.07
     serializer
    -0.07
    ;text
    -0.07
    ,text
    -0.07
    Memcpy
    -0.07
    Coffee
    -0.07
    POSITIVE LOGITS
     Ib
    0.07
     Israël
    0.07
     recess
    0.07
    皇
    0.07
     devlet
    0.07
    reece
    0.07
     držav
    0.07
     lave
    0.06
     Castle
    0.06
     philosophie
    0.06
    Activations Density 1.234%

    No Known Activations