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. 49021
    Prev
    Next
    INDEX
    Explanations

    y

    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
     Db
    -0.08
     Immutable
    -0.08
     Lastly
    -0.08
     Renewal
    -0.08
    -buttons
    -0.08
     errands
    -0.08
    ulif
    -0.08
     NSMutable
    -0.08
     renewal
    -0.07
    截止
    -0.07
    POSITIVE LOGITS
    ±
    0.10
     ±
    0.10
    สู
    0.09
     proportional
    0.09
     +/-
    0.08
     RMS
    0.08
    vah
    0.08
    chet
    0.08
    (+
    0.07
    川
    0.07
    Activations Density 0.013%

    No Known Activations