© 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. 49695
    Prev
    Next
    INDEX
    Explanations

    ge

    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
     טוב
    -0.08
     archivos
    -0.08
     фай
    -0.08
    iječ
    -0.08
    _keeper
    -0.07
    梅
    -0.07
    irió
    -0.07
     آهي
    -0.07
    ир
    -0.07
     irons
    -0.07
    POSITIVE LOGITS
    assemble
    0.10
    probeerd
    0.09
    ïnv
    0.09
    actual
    0.09
    produce
    0.08
    üp
    0.08
    ënte
    0.08
    relation
    0.08
    assoc
    0.08
    imple
    0.08
    Activations Density 0.000%

    No Known Activations