© 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. 99163
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Turqu
    -0.08
    yre
    -0.07
     Pass
    -0.07
    üre
    -0.07
    Lib
    -0.07
    Pass
    -0.07
     jurídica
    -0.07
     Verdict
    -0.07
     critiques
    -0.07
    Restart
    -0.07
    POSITIVE LOGITS
    semantic
    0.09
     semiconductor
    0.09
    -sem
    0.09
     veeb
    0.09
     cartons
    0.09
     Geschenk
    0.09
     tetra
    0.08
     cubes
    0.08
    网上
    0.08
     verkk
    0.08
    Activations Density 0.020%

    No Known Activations