© 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 EvalsExportsAPI 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. 49744
    Prev
    Next
    INDEX
    Explanations

    、

    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
     Rossi
    -0.09
     June
    -0.08
    ҷ
    -0.08
    ocas
    -0.07
    visit
    -0.07
    emt
    -0.07
    $c
    -0.07
    dashboard
    -0.07
    .visit
    -0.07
    firm
    -0.07
    POSITIVE LOGITS
     teile
    0.08
     defect
    0.08
     αντα
    0.08
     ৰ
    0.08
     हुँ
    0.08
    assle
    0.07
     반
    0.07
     carrot
    0.07
    -ca
    0.07
    ター
    0.07
    Activations Density 0.000%

    No Known Activations