© 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. 19-RESID-POST-AA
    11. 18946
    Prev
    Next
    INDEX
    Explanations

    say "dig" 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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FFFFFF
    -0.08
    ABCDE
    -0.08
    loat
    -0.08
    _Custom
    -0.08
    FFF
    -0.08
     Blend
    -0.08
    _AST
    -0.08
    _A
    -0.08
     blend
    -0.08
    hla
    -0.08
    POSITIVE LOGITS
     digits
    0.12
    digits
    0.12
    _digits
    0.12
     DIG
    0.11
     digit
    0.11
    igits
    0.10
     cyfr
    0.10
    Digits
    0.10
    digit
    0.10
     циф
    0.10
    Activations Density 0.003%

    No Known Activations