© 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. 5931
    Prev
    Next
    INDEX
    Explanations

    Foreign languages, math, code

    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
    પ
    -0.09
    F
    -0.08
     F
    -0.07
    ફ
    -0.07
     bị
    -0.07
     sin
    -0.07
     adgang
    -0.07
    स्क
    -0.07
    ícola
    -0.07
     U
    -0.07
    POSITIVE LOGITS
    (REG
    0.09
    ah
    0.08
    cout
    0.08
    .REG
    0.08
    <iostream
    0.08
    "B
    0.08
    'hésitez
    0.08
    шее
    0.08
    =B
    0.08
    stro
    0.08
    Activations Density 0.021%

    No Known Activations