© 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. 3-RESID-POST-AA
    11. 2596
    Prev
    Next
    INDEX
    Explanations

    full stop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yata
    -0.08
     Ebene
    -0.07
     Mol
    -0.07
     oficina
    -0.07
     rode
    -0.07
     hypoc
    -0.07
     Wohl
    -0.07
    вай
    -0.07
    ευ
    -0.07
     physi
    -0.07
    POSITIVE LOGITS
    ��
    0.08
     â
    0.08
    Â
    0.08
     congen
    0.07
    .un
    0.07
     بال
    0.07
     borderline
    0.07
    .Â
    0.07
    .ul
    0.07
    <|reserved_200016|>
    0.07
    Activations Density 0.097%

    No Known Activations