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. 12686
    Prev
    Next
    INDEX
    Explanations

    of

    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
     paras
    -0.08
     represents
    -0.08
    oinen
    -0.08
     prevent
    -0.08
    /File
    -0.08
     Paras
    -0.07
    也是
    -0.07
    AGS
    -0.07
    prevent
    -0.07
     predstavlja
    -0.07
    POSITIVE LOGITS
    ницу
    0.08
    Ig
    0.07
     variable
    0.07
     Calm
    0.07
     afirm
    0.07
     Ig
    0.07
    ница
    0.07
     demol
    0.07
    ицу
    0.07
     aunt
    0.07
    Activations Density 0.001%

    No Known Activations