© 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. 6298
    Prev
    Next
    INDEX
    Explanations

    Library metadata

    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
    搬
    -0.08
    _OBJ
    -0.08
    merking
    -0.07
    Father
    -0.07
     conseille
    -0.07
    father
    -0.07
     disables
    -0.07
     statut
    -0.07
    �
    -0.07
    fører
    -0.07
    POSITIVE LOGITS
     authorized
    0.09
     വർ
    0.08
     classified
    0.08
     paka
    0.08
     classificados
    0.08
     koos
    0.08
     zaidi
    0.08
    Authorized
    0.08
     Klass
    0.08
     Classified
    0.08
    Activations Density 0.000%

    No Known Activations