© 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. 96942
    Prev
    Next
    INDEX
    Explanations

    ед

    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
    ür
    -0.08
    ör
    -0.08
    ønd
    -0.08
     realization
    -0.08
     går
    -0.08
    ob
    -0.08
    ограф
    -0.08
    eng
    -0.08
     gikk
    -0.08
    ont
    -0.07
    POSITIVE LOGITS
    ികളും
    0.09
    ികളുടെ
    0.08
    INC
    0.08
    ини
    0.08
     ylim
    0.08
    ителей
    0.08
     reh
    0.08
     thanh
    0.08
    ിണ
    0.08
     recessed
    0.08
    Activations Density 0.000%

    No Known Activations