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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11730
    Prev
    Next
    INDEX
    Explanations

    larva

    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
     loved
    -0.08
     breeding
    -0.08
     naro
    -0.08
     nascimento
    -0.07
    losti
    -0.07
     birthday
    -0.07
     nacimiento
    -0.07
     elemento
    -0.07
    алоу
    -0.07
     rpc
    -0.07
    POSITIVE LOGITS
    709
    0.08
     berupa
    0.08
     AMS
    0.08
     Keb
    0.08
     Staaten
    0.08
     Stable
    0.08
     Stefan
    0.08
     CMA
    0.07
    _stop
    0.07
     doubts
    0.07
    Activations Density 0.002%

    No Known Activations