© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29115
    Prev
    Next
    INDEX
    Explanations

    and

    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
     చెందిన
    -0.08
    -valu
    -0.08
    ಿಸಲಾಗ
    -0.08
    を
    -0.08
    를
    -0.07
    -0.07
    ిస్త
    -0.07
    하려
    -0.07
    .s
    -0.07
    ISO
    -0.07
    POSITIVE LOGITS
     unfor
    0.09
    gone
    0.08
    ubon
    0.08
     उठा
    0.08
    keen
    0.08
     fierce
    0.08
     enth
    0.08
     aufreg
    0.08
    athi
    0.08
     behold
    0.08
    Activations Density 0.028%
    No Known Activations