© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69460
    Prev
    Next
    INDEX
    Explanations

    says

    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
    unningham
    -0.08
    GM
    -0.08
    _____
    -0.08
     Hem
    -0.07
     Southern
    -0.07
    akt
    -0.07
    TMP
    -0.07
    ifra
    -0.07
    AK
    -0.07
     गर्नु
    -0.07
    POSITIVE LOGITS
     unspecified
    0.08
     stated
    0.07
     explicitly
    0.07
    usest
    0.07
     واضحة
    0.07
     topl
    0.07
    וס
    0.07
     satisf
    0.07
     vague
    0.07
    mention
    0.07
    Activations Density 0.091%

    No Known Activations