© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96901
    Prev
    Next
    INDEX
    Explanations

    Hungarian language

    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
    $id
    -0.08
     XII
    -0.08
    Staff
    -0.08
    Aud
    -0.08
    [...]↵↵
    -0.08
    ounding
    -0.08
    CCE
    -0.08
    ствия
    -0.07
    Women
    -0.07
    XC
    -0.07
    POSITIVE LOGITS
     adopt
    0.09
     reciben
    0.08
     adoptar
    0.07
     fing
    0.07
     Adoption
    0.07
     adopting
    0.07
     sunk
    0.07
     participación
    0.07
     océ
    0.07
     hervor
    0.07
    Activations Density 0.000%

    No Known Activations