© 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. 110616
    Prev
    Next
    INDEX
    Explanations

    processes

    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
    机构
    -0.07
     killed
    -0.07
    _rng
    -0.07
     написал
    -0.07
    -system
    -0.07
    $↵↵
    -0.07
    cev
    -0.07
    孩
    -0.07
    ರ್ಜ
    -0.07
     configurable
    -0.07
    POSITIVE LOGITS
     ohnehin
    0.09
     sırasında
    0.09
     kapsamında
    0.08
    Maintain
    0.08
    에서도
    0.08
     muuten
    0.08
    ాల్లో
    0.08
    otherwise
    0.08
     전에
    0.08
     بالخ
    0.08
    Activations Density 0.626%

    No Known Activations