© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70731
    Prev
    Next
    INDEX
    Explanations

    并

    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
     Rules
    -0.07
     reverted
    -0.07
     관리자
    -0.07
     Cover
    -0.07
     Mask
    -0.07
     Tournament
    -0.07
     الداخلية
    -0.07
     Little
    -0.07
     Last
    -0.07
    ್ಯೂ
    -0.07
    POSITIVE LOGITS
     simult
    0.10
     simultaneous
    0.08
    -channel
    0.08
     միաս
    0.08
     vib
    0.08
     concom
    0.08
    -market
    0.08
    preci
    0.08
    aligned
    0.08
    viv
    0.08
    Activations Density 0.007%

    No Known Activations