© 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. 91481
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    &nbsp
    -0.08
    ->
    -0.08
     Cru
    -0.07
     alike
    -0.07
    .A
    -0.07
     controller
    -0.07
     Reads
    -0.07
    Sv
    -0.07
    >"↵
    -0.07
    .like
    -0.07
    POSITIVE LOGITS
     domu
    0.09
     ندار
    0.09
     nél
    0.08
     싶
    0.08
     너무
    0.08
     familial
    0.08
    なら
    0.08
     సూ�
    0.08
     కాక
    0.08
     hesitate
    0.08
    Activations Density 0.939%

    No Known Activations