© 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. 19-RESID-POST-AA
    11. 102647
    Prev
    Next
    INDEX
    Explanations

    there

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     давно
    -0.09
     бир
    -0.09
     دارای
    -0.09
     різ
    -0.08
     विविध
    -0.08
     diversified
    -0.08
     varied
    -0.08
     возмож
    -0.08
     бір
    -0.08
     разнообраз
    -0.07
    POSITIVE LOGITS
     arises
    0.11
     be
    0.10
     corresponds
    0.09
     geldt
    0.09
     arise
    0.09
    be
    0.09
    abouts
    0.08
    /">
    0.08
    avior
    0.08
    ுடைய
    0.08
    Activations Density 0.041%

    No Known Activations