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. 52694
    Prev
    Next
    INDEX
    Explanations

    macro

    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
    -0.08
     beaches
    -0.07
     playas
    -0.07
     ESA
    -0.07
     sept
    -0.07
     ayr
    -0.07
    obalt
    -0.07
     playa
    -0.07
    中央
    -0.07
     Playa
    -0.07
    POSITIVE LOGITS
     шаб
    0.08
    Ol
    0.08
     medic
    0.08
     foam
    0.08
     deaf
    0.08
     만들어
    0.07
     Stol
    0.07
     Foam
    0.07
    _VOID
    0.07
    jat
    0.07
    Activations Density 0.003%

    No Known Activations