© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110715
    Prev
    Next
    INDEX
    Explanations

    Misuse of "times" (math)

    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
     Pilot
    -0.08
     Tail
    -0.08
     سول
    -0.07
    Tail
    -0.07
     renom
    -0.07
     принадлеж
    -0.07
    inya
    -0.07
     vite
    -0.07
     Laurent
    -0.07
     שם
    -0.07
    POSITIVE LOGITS
     notoriously
    0.11
     misleading
    0.09
    _USAGE
    0.09
     extravagant
    0.09
     ambiguous
    0.08
     collo
    0.08
    _FP
    0.08
     unreliable
    0.08
    PCM
    0.08
    Percentage
    0.08
    Activations Density 0.027%

    No Known Activations