© 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 EvalsExportsAPI 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. 49622
    Prev
    Next
    INDEX
    Explanations

    say "ic" words

    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
    île
    -0.09
    lisle
    -0.08
    ებაა
    -0.08
    letso
    -0.08
     siete
    -0.08
    ’île
    -0.08
    ილია
    -0.08
    აა
    -0.08
    ligne
    -0.08
     satisfait
    -0.08
    POSITIVE LOGITS
    ican
    0.10
    icus
    0.10
     uhl
    0.08
    ിൻ
    0.08
     проблему
    0.07
    feld
    0.07
     enforce
    0.07
    wagon
    0.07
    	net
    0.07
     ziehen
    0.07
    Activations Density 0.001%

    No Known Activations