© 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. 11-RESID-POST-AA
    11. 75645
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ರ್ಭ
    -0.08
    Carol
    -0.08
    _serializer
    -0.08
     betrekking
    -0.08
    _col
    -0.08
     passou
    -0.08
    ทรู
    -0.07
    😊
    -0.07
    .uni
    -0.07
    Adam
    -0.07
    POSITIVE LOGITS
     quasi
    0.08
     Extras
    0.08
    -|
    0.07
     kelle
    0.07
    mitteln
    0.07
     multifunction
    0.07
     Nicht
    0.07
     Shirley
    0.07
     courtyard
    0.07
     kish
    0.07
    Activations Density 0.174%

    No Known Activations