© 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. 95391
    Prev
    Next
    INDEX
    Explanations

    Software installation instructions involving Windows

    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
     merch
    -0.08
     情
    -0.08
    program
    -0.07
    ણે
    -0.07
    (direction
    -0.07
     tré
    -0.07
     eig
    -0.07
    صى
    -0.07
     제품
    -0.07
     femin
    -0.07
    POSITIVE LOGITS
     Enlarg
    0.10
     Enlargement
    0.08
    ției
    0.08
    _
    0.08
     TW
    0.08
    erseits
    0.08
     unwilling
    0.07
     enlarge
    0.07
     Nest
    0.07
     This
    0.07
    Activations Density 0.000%

    No Known Activations