© 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. 23-RESID-POST-AA
    11. 50520
    Prev
    Next
    INDEX
    Explanations

    say "r word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ахь
    -0.08
     Regional
    -0.07
     Rein
    -0.07
     Reason
    -0.07
     Regel
    -0.07
    ibas
    -0.07
    _REG
    -0.07
    ويه
    -0.07
     faʻ
    -0.07
    _REL
    -0.07
    POSITIVE LOGITS
     r
    0.73
    (r
    0.62
    	r
    0.61
    =r
    0.60
    ,r
    0.59
    r
    0.57
    *r
    0.56
    [r
    0.53
    $r
    0.52
    :r
    0.52
    Activations Density 0.624%

    No Known Activations