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. 111793
    Prev
    Next
    INDEX
    Explanations

    positive

    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
    modell
    -0.08
     destinada
    -0.08
     destinados
    -0.08
    rans
    -0.07
     opener
    -0.07
     Racer
    -0.07
     Don
    -0.07
     RAC
    -0.07
     QA
    -0.07
    _RUNNING
    -0.07
    POSITIVE LOGITS
     الفض
    0.08
     હો
    0.08
     possibility
    0.07
    <<
    0.07
    Hint
    0.07
    avos
    0.07
     conveniently
    0.07
    <My
    0.07
    <Service
    0.07
     Pun
    0.07
    Activations Density 0.073%

    No Known Activations