© 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. 96679
    Prev
    Next
    INDEX
    Explanations

    letter x

    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
    �
    -0.08
     acteurs
    -0.08
    /business
    -0.07
     empresários
    -0.07
     brick
    -0.07
     пузыр
    -0.07
     Vertreter
    -0.07
    /property
    -0.07
     avantaj
    -0.07
    砖
    -0.07
    POSITIVE LOGITS
     x
    0.16
    x
    0.12
    	x
    0.12
    "x
    0.11
    xdb
    0.10
    xda
    0.10
    =x
    0.09
     ×
    0.09
    xa
    0.09
    $x
    0.09
    Activations Density 0.003%

    No Known Activations