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. 98337
    Prev
    Next
    INDEX
    Explanations

    Recipes

    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
    -0.07
    arily
    -0.07
     generally
    -0.07
    xbb
    -0.07
    :x
    -0.07
    [x
    -0.07
     briefly
    -0.07
     generale
    -0.07
     Qo
    -0.06
     knowing
    -0.06
    POSITIVE LOGITS
     precioso
    0.09
    ॉक
    0.09
    ből
    0.08
     pev
    0.08
    ण
    0.08
     amháin
    0.08
     Ngunit
    0.08
     preciosa
    0.08
     अलावा
    0.08
     හා
    0.08
    Activations Density 0.054%

    No Known Activations