© 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. 96712
    Prev
    Next
    INDEX
    Explanations

    оп

    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
    ס
    -0.09
    .Re
    -0.08
     Rechts
    -0.08
    ANSI
    -0.07
    /user
    -0.07
    apers
    -0.07
    ent
    -0.07
     UNIX
    -0.07
     Ges
    -0.07
     unus
    -0.07
    POSITIVE LOGITS
     круж
    0.08
     lave
    0.08
     uyğun
    0.08
     olul
    0.08
     meadow
    0.08
     maga
    0.08
     sən
    0.08
     puck
    0.08
     cual
    0.08
     çò
    0.08
    Activations Density 0.000%

    No Known Activations