© 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. 23-RESID-POST-AA
    11. 48639
    Prev
    Next
    INDEX
    Explanations

    academic papers or numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Qt
    -0.09
    Qt
    -0.09
     QQ
    -0.08
     interactieve
    -0.08
    _sensitive
    -0.08
    itesi
    -0.08
     biggest
    -0.07
    QQ
    -0.07
    interactive
    -0.07
     destru
    -0.07
    POSITIVE LOGITS
    .ai
    0.07
    ignes
    0.07
    #{
    0.07
     εγ
    0.07
    _W
    0.07
    877
    0.07
    .Space
    0.07
     Space
    0.07
    022
    0.07
    009
    0.07
    Activations Density 0.014%

    No Known Activations