© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96916
    Prev
    Next
    INDEX
    Explanations

    Author names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Click
    -0.08
    -elect
    -0.08
    r
    -0.08
    .Pointer
    -0.08
    flatten
    -0.08
    -gl
    -0.08
     horen
    -0.07
    -global
    -0.07
    /K
    -0.07
    -render
    -0.07
    POSITIVE LOGITS
    prüche
    0.08
     available
    0.08
     lượt
    0.08
     disponíveis
    0.08
     Results
    0.08
     Him
    0.08
    Ń
    0.08
     resultados
    0.08
    _results
    0.08
    жаў
    0.08
    Activations Density 0.001%

    No Known Activations