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. 74968
    Prev
    Next
    INDEX
    Explanations

    Roche/Creed

    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
    -gradient
    -0.08
    _ant
    -0.08
    -AM
    -0.08
    -ant
    -0.08
     �
    -0.08
    .nc
    -0.08
    ّن
    -0.08
    -responsive
    -0.08
    Resposta
    -0.08
    -link
    -0.07
    POSITIVE LOGITS
     fine
    0.09
     legally
    0.09
     forbidden
    0.09
     forbid
    0.08
     allowable
    0.08
     Forbidden
    0.08
     meat
    0.08
     legal
    0.08
     late
    0.08
     distinct
    0.08
    Activations Density 0.001%

    No Known Activations