© 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. 30074
    Prev
    Next
    INDEX
    Explanations

    logarithm

    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
    _hour
    -0.08
    홀
    -0.08
     lectus
    -0.08
     spaz
    -0.08
     cus
    -0.07
    agrant
    -0.07
     tonight
    -0.07
     days
    -0.07
     attente
    -0.07
     acol
    -0.07
    POSITIVE LOGITS
    普通
    0.09
     પ્રમાણ
    0.08
     numerator
    0.08
     convencional
    0.07
     동일
    0.07
     מקור
    0.07
     промеж
    0.07
     kompl
    0.07
    จำ
    0.07
    .Normal
    0.07
    Activations Density 0.015%

    No Known Activations