© 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. 96906
    Prev
    Next
    INDEX
    Explanations

    odpow

    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
    .Throw
    -0.08
    SUCCESS
    -0.08
     SUCCESS
    -0.08
     succeed
    -0.08
     CORE
    -0.08
    ाश
    -0.08
     vire
    -0.07
    Requested
    -0.07
     success
    -0.07
     criou
    -0.07
    POSITIVE LOGITS
    іда
    0.16
    iada
    0.15
    iad
    0.10
    сю
    0.09
    iedz
    0.09
    іла
    0.09
    яда
    0.08
    ied
    0.08
    owied
    0.08
    வற்ற
    0.08
    Activations Density 0.001%

    No Known Activations