© 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. 704
    Prev
    Next
    INDEX
    Explanations

    match

    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
     hit
    -0.08
     darstellen
    -0.08
     하면
    -0.08
    _hit
    -0.07
    _Ver
    -0.07
     differences
    -0.07
     kiểm
    -0.07
     revue
    -0.07
     überprüfen
    -0.07
     pertama
    -0.07
    POSITIVE LOGITS
    万元
    0.08
     tumult
    0.08
     Oro
    0.08
     Las
    0.08
    Intensity
    0.08
    /we
    0.08
    klif
    0.08
     Atem
    0.08
    kapet
    0.08
     уров
    0.08
    Activations Density 0.017%

    No Known Activations