© 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. 24656
    Prev
    Next
    INDEX
    Explanations

    Code counting lines

    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
    .PREFERRED
    -0.08
    ktrum
    -0.08
     delen
    -0.08
     Griffin
    -0.08
     Recommended
    -0.08
    Schedule
    -0.07
    _schedule
    -0.07
    _activate
    -0.07
    ète
    -0.07
     Authorized
    -0.07
    POSITIVE LOGITS
     counting
    0.21
     Counting
    0.20
    Counting
    0.20
    .count
    0.20
     counted
    0.19
     counts
    0.19
    .Count
    0.18
     count
    0.18
     COUNT
    0.17
    	count
    0.17
    Activations Density 0.031%

    No Known Activations