© 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. 706
    Prev
    Next
    INDEX
    Explanations

    Subtraction problems

    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
    pero
    -0.08
    omitempty
    -0.08
     nossa
    -0.08
     breathable
    -0.08
    velop
    -0.08
    ทั่วไป
    -0.08
    [...,
    -0.07
     faith
    -0.07
    clr
    -0.07
    ouring
    -0.07
    POSITIVE LOGITS
     losses
    0.09
    Subtract
    0.09
     tally
    0.09
     Removed
    0.09
     deducted
    0.09
     Undo
    0.09
    Removed
    0.09
     जिसने
    0.09
     casualties
    0.08
     deduction
    0.08
    Activations Density 0.050%

    No Known Activations