© 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. 78365
    Prev
    Next
    INDEX
    Explanations

    federalist

    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
    -0.09
     Allow
    -0.07
    =h
    -0.07
    provid
    -0.07
    .min
    -0.07
    =None
    -0.07
    _lat
    -0.07
     lightly
    -0.07
    .prevent
    -0.07
    .includes
    -0.07
    POSITIVE LOGITS
     ente
    0.09
     conglomer
    0.09
    éis
    0.08
     intenz
    0.08
     Functions
    0.08
    0.08
     Aprove
    0.08
     fenêtre
    0.08
     difusión
    0.08
    فادة
    0.08
    Activations Density 0.000%
    No Known Activations