Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42156
    Prev
    Next
    INDEX
    Explanations

    JSON

    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
     probability
    -0.09
    Probability
    -0.08
    _Impl
    -0.07
     confidence
    -0.07
     sentiments
    -0.07
     grades
    -0.07
     다음
    -0.07
     السنة
    -0.07
     proficiency
    -0.07
     난
    -0.07
    POSITIVE LOGITS
    .stringify
    0.09
     beper
    0.08
    כלה
    0.08
     parecia
    0.08
     prehr
    0.08
    իկոլ
    0.08
     փորձ
    0.08
     kunne
    0.08
     Rey
    0.07
     divorced
    0.07
    Activations Density 0.001%

    No Known Activations