© 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. 97439
    Prev
    Next
    INDEX
    Explanations

    通

    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
     Bumble
    -0.10
     muff
    -0.08
     Mimi
    -0.08
     milion
    -0.08
    ्यम
    -0.08
    ABCDEFG
    -0.08
    ajaj
    -0.08
    Million
    -0.08
    376
    -0.08
     jedan
    -0.08
    POSITIVE LOGITS
    路
    0.12
    _routes
    0.08
     मार्क
    0.07
    ittäin
    0.07
     interpolation
    0.07
    .Notify
    0.07
     actuator
    0.07
     standpoint
    0.07
    ड़ों
    0.07
    asin
    0.07
    Activations Density 0.001%

    No Known Activations