© 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. 108772
    Prev
    Next
    INDEX
    Explanations

    {

    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
     baka
    -0.08
     lyric
    -0.08
    wife
    -0.07
     dum
    -0.07
    stats
    -0.07
    bmp
    -0.07
    fullname
    -0.07
    rip
    -0.07
     bigger
    -0.07
    decision
    -0.07
    POSITIVE LOGITS
     بـ
    0.08
    (Data
    0.08
     elsif
    0.08
    робнее
    0.08
     KOM
    0.08
     لأنها
    0.08
     elseif
    0.08
    .Errors
    0.07
     Data
    0.07
     ers
    0.07
    Activations Density 0.007%

    No Known Activations