© 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. 29665
    Prev
    Next
    INDEX
    Explanations

    line

    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
     enorme
    -0.08
     Fehl
    -0.08
     impose
    -0.07
    _errno
    -0.07
     accolades
    -0.07
     এতে
    -0.07
    ikations
    -0.07
    奥
    -0.07
     כאן
    -0.07
    hist
    -0.07
    POSITIVE LOGITS
     vicinity
    0.09
     aforementioned
    0.09
    enig
    0.08
     perpendicular
    0.08
    FID
    0.08
     zašt
    0.08
    чә
    0.08
     Settlement
    0.08
     RO
    0.08
    Settlement
    0.07
    Activations Density 0.025%

    No Known Activations