© 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. 75541
    Prev
    Next
    INDEX
    Explanations

    passphrase

    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
     insults
    -0.09
     Halloween
    -0.08
    voja
    -0.08
     满
    -0.08
     Credential
    -0.07
    قت
    -0.07
    rape
    -0.07
     యొక్క
    -0.07
    curso
    -0.07
    .Div
    -0.07
    POSITIVE LOGITS
    લ
    0.07
     charset
    0.07
     berharap
    0.07
     gerade
    0.07
     ضخ
    0.07
     bursting
    0.07
     langsam
    0.07
     қол
    0.07
    _BUCKET
    0.07
     wäre
    0.07
    Activations Density 0.001%

    No Known Activations