© 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. 48200
    Prev
    Next
    INDEX
    Explanations

    зав

    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
     zodat
    -0.09
     staging
    -0.08
     auth
    -0.08
     nab
    -0.07
     insure
    -0.07
    ಾರ್
    -0.07
    so
    -0.07
     ert
    -0.07
     d
    -0.07
    baan
    -0.07
    POSITIVE LOGITS
    и
    0.12
    �
    0.09
    язан
    0.08
    ల
    0.08
     г
    0.08
    针
    0.08
    isé
    0.07
     pendent
    0.07
     bubble
    0.07
    гел
    0.07
    Activations Density 0.001%

    No Known Activations