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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45657
    Prev
    Next
    INDEX
    Explanations

    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
     manoe
    -0.08
     expertly
    -0.08
     maneuver
    -0.08
     کیفیت
    -0.07
                 ↵
    -0.07
     monitored
    -0.07
     विशेषज्ञ
    -0.07
    轉
    -0.07
    -0.07
    .duration
    -0.07
    POSITIVE LOGITS
     Ainsi
    0.10
    .symmetric
    0.10
     symmetrical
    0.09
     symmetric
    0.09
     parity
    0.09
    _encrypt
    0.09
     symmetry
    0.09
    Ainsi
    0.08
     antis
    0.08
     Sym
    0.08
    Activations Density 0.079%

    No Known Activations