© 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. 11-RESID-POST-AA
    11. 94905
    Prev
    Next
    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Male
    -0.08
    Fi
    -0.08
    gender
    -0.07
     полу
    -0.07
    ế
    -0.07
     белән
    -0.07
     Vé
    -0.07
    Male
    -0.07
     haqida
    -0.07
    :Add
    -0.07
    POSITIVE LOGITS
     desto
    0.12
     chance
    0.10
    ier
    0.09
    、更
    0.09
     chances
    0.09
    stown
    0.08
     likelihood
    0.08
     maior
    0.08
     proportion
    0.08
     càng
    0.08
    Activations Density 0.075%

    No Known Activations