© 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. 97324
    Prev
    Next
    INDEX
    Explanations

    say "че"

    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
     Salvador
    -0.07
    .<
    -0.07
    .Room
    -0.07
     alternate
    -0.07
    .registry
    -0.07
     screens
    -0.07
     room
    -0.07
     rule
    -0.07
    .),
    -0.07
     rooms
    -0.07
    POSITIVE LOGITS
     տեղի
    0.09
     digwydd
    0.09
    iaal
    0.09
    иғ
    0.08
    -log
    0.08
    иф
    0.08
    ыц
    0.08
     വരുന്ന
    0.08
    глав
    0.08
     plaatsvinden
    0.08
    Activations Density 0.000%

    No Known Activations