© 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. 47952
    Prev
    Next
    INDEX
    Explanations

    Adherence

    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
     searching
    -0.08
    .Transparent
    -0.08
     Searching
    -0.08
    Searching
    -0.08
    Trans
    -0.08
     envolvendo
    -0.08
    Shade
    -0.08
    Pig
    -0.08
     Curious
    -0.07
    .an
    -0.07
    POSITIVE LOGITS
     medication
    0.11
     uptake
    0.10
     Medication
    0.10
    努力
    0.10
     العلاج
    0.09
     પ્રય
    0.09
     thérape
    0.09
     terapi
    0.09
     DVR
    0.09
     diligence
    0.09
    Activations Density 0.009%

    No Known Activations