© 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. 23-RESID-POST-AA
    11. 50477
    Prev
    Next
    INDEX
    Explanations

    加

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Extension
    -0.07
     rack
    -0.07
    halter
    -0.07
    (extension
    -0.07
    Combination
    -0.07
     доп
    -0.07
     помощ
    -0.07
     অত
    -0.07
     improving
    -0.07
    _extension
    -0.07
    POSITIVE LOGITS
    剧
    0.14
    劇
    0.12
    剧情
    0.09
     તે�
    0.09
    ismic
    0.09
     combustível
    0.09
     Macbeth
    0.08
    สปีด
    0.08
     المسر
    0.08
     du
    0.08
    Activations Density 0.001%

    No Known Activations