© 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. 3-RESID-POST-AA
    11. 2544
    Prev
    Next
    INDEX
    Explanations

    Subtraction/assignment expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offici
    -0.08
     egentligen
    -0.07
    .Tile
    -0.07
    organic
    -0.07
     endeavor
    -0.07
     lit
    -0.07
    )을
    -0.07
    야
    -0.07
     coher
    -0.07
     Lit
    -0.07
    POSITIVE LOGITS
    掉
    0.12
     widespread
    0.08
     drastic
    0.07
     hiatus
    0.07
     அவ
    0.07
     Philip
    0.07
    oods
    0.07
     inplace
    0.07
     entgegen
    0.07
     dimensional
    0.07
    Activations Density 0.008%

    No Known Activations