© 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. 83
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Dre
    -0.07
    多久
    -0.07
     diversified
    -0.07
    DU
    -0.07
     depending
    -0.07
    Due
    -0.07
     discus
    -0.07
    舍
    -0.07
     dosing
    -0.07
     plupart
    -0.07
    POSITIVE LOGITS
     wrongly
    0.10
     falsch
    0.10
     unjust
    0.10
     inappropriate
    0.10
     abusing
    0.10
     violating
    0.10
     falsely
    0.10
    _failure
    0.09
     improperly
    0.09
     misuse
    0.09
    Activations Density 0.015%

    No Known Activations