© 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. 3-RESID-POST-AA
    11. 2501
    Prev
    Next
    INDEX
    Explanations

    xpath

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ═
    -0.09
     Dana
    -0.08
     Marshall
    -0.07
    uous
    -0.07
     menjal
    -0.07
     Tobias
    -0.07
    ுண
    -0.07
    Basket
    -0.07
     Johnston
    -0.07
     Papa
    -0.07
    POSITIVE LOGITS
    elja
    0.08
    -cont
    0.08
    赏
    0.08
     eminent
    0.07
    enix
    0.07
    өө
    0.07
     fiss
    0.07
     ವ್ಯಾಪ
    0.07
     surgeries
    0.07
     ile
    0.07
    Activations Density 0.002%

    No Known Activations