© 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. 44791
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     couvert
    -0.09
    rụ
    -0.09
    idro
    -0.09
    াঘ
    -0.08
    criminal
    -0.08
     exercised
    -0.08
     sommer
    -0.08
    첫
    -0.08
    LOPT
    -0.08
    ког
    -0.08
    POSITIVE LOGITS
     bake
    0.07
    697
    0.07
     uppercase
    0.07
     analogue
    0.07
    383
    0.07
    ーワ
    0.07
    (push
    0.07
    ELE
    0.07
    (out
    0.07
    .special
    0.07
    Activations Density 0.028%

    No Known Activations