© 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. 111288
    Prev
    Next
    INDEX
    Explanations

    urado

    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
     anual
    -0.07
    .apache
    -0.07
     झ
    -0.07
     wa
    -0.07
    Wind
    -0.07
     Annual
    -0.07
     wind
    -0.07
     annual
    -0.07
    [w
    -0.07
    ాంక
    -0.07
    POSITIVE LOGITS
     you'd
    0.09
     пригод
    0.08
    вам
    0.08
     you're
    0.08
     യോഗ
    0.08
     вам
    0.08
    PQ
    0.08
    ('.');↵
    0.08
     നിങ്ങൾ
    0.07
    yi
    0.07
    Activations Density 0.002%

    No Known Activations