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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91185
    Prev
    Next
    INDEX
    Explanations

    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
    irano
    -0.08
    .team
    -0.08
     Pair
    -0.08
    esian
    -0.07
     suppose
    -0.07
     taut
    -0.07
    past
    -0.07
    ydd
    -0.07
    rolog
    -0.07
    깔
    -0.07
    POSITIVE LOGITS
    是多少
    0.11
     જેટ
    0.10
     kadar
    0.09
     വരെ
    0.08
    ോളം
    0.08
     Makeup
    0.08
     आंक
    0.08
     prol
    0.07
     díky
    0.07
    甚至
    0.07
    Activations Density 0.359%

    No Known Activations