© 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. 11-RESID-POST-AA
    11. 99385
    Prev
    Next
    INDEX
    Explanations

    ode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     گیری
    -0.08
     звон
    -0.08
     Schmidt
    -0.08
     upbeat
    -0.08
     стих
    -0.08
     Dav
    -0.08
     policeman
    -0.07
     prosper
    -0.07
    (regex
    -0.07
     halb
    -0.07
    POSITIVE LOGITS
     erosion
    0.10
    trust
    0.09
     trust
    0.09
     weakening
    0.08
     tolerance
    0.08
    掉
    0.08
     credibility
    0.08
    削
    0.08
     Southern
    0.08
     Trust
    0.07
    Activations Density 0.007%

    No Known Activations