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. 87915
    Prev
    Next
    INDEX
    Explanations

    coli

    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
    Settings
    -0.08
     SINGLE
    -0.08
     rä
    -0.07
    .settings
    -0.07
     că
    -0.07
     систему
    -0.07
    fully
    -0.07
    _settings
    -0.07
    .DEFAULT
    -0.07
     cascading
    -0.07
    POSITIVE LOGITS
     Patagonia
    0.08
    ؤ
    0.08
     ورب
    0.08
    MN
    0.08
    طرح
    0.08
    halt
    0.07
     �
    0.07
    ُّ
    0.07
     Existe
    0.07
    endor
    0.07
    Activations Density 0.001%

    No Known Activations