© 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. 44882
    Prev
    Next
    INDEX
    Explanations

    outside

    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
    Claire
    -0.07
    might
    -0.07
     бель
    -0.07
     hygiene
    -0.07
    Belg
    -0.07
    pipeline
    -0.07
     Belgium
    -0.07
    חשב
    -0.07
    mand
    -0.07
     may
    -0.07
    POSITIVE LOGITS
     extremes
    0.12
     extrema
    0.11
     extreme
    0.10
     extrem
    0.10
     Extrem
    0.10
     corners
    0.09
    分别
    0.09
     ekstrem
    0.09
    禽
    0.09
     extremos
    0.09
    Activations Density 0.054%

    No Known Activations