© 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. 502
    Prev
    Next
    INDEX
    Explanations

    code skipping/ignoring

    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
     Salv
    -0.09
     Mann
    -0.08
     Presents
    -0.08
     Morton
    -0.08
     eur
    -0.08
    icits
    -0.08
     daraus
    -0.08
    Mort
    -0.07
     Siege
    -0.07
     Eleanor
    -0.07
    POSITIVE LOGITS
    AV
    0.09
    /filter
    0.09
    /include
    0.09
    .skip
    0.08
    mask
    0.08
    /sk
    0.08
     AV
    0.08
    recognized
    0.08
    criteria
    0.08
    .j
    0.08
    Activations Density 0.004%

    No Known Activations