Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48338
    Prev
    Next
    INDEX
    Explanations

    say "о" 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
    .au
    -0.08
     enabled
    -0.08
     Surat
    -0.07
     cake
    -0.07
     offenbar
    -0.07
     gái
    -0.07
     が
    -0.07
    -general
    -0.07
     evident
    -0.07
     fats
    -0.07
    POSITIVE LOGITS
    омы
    0.09
    ENUM
    0.08
     তো
    0.08
    aner
    0.08
    aso
    0.08
    อต
    0.07
     केंद
    0.07
    ires
    0.07
     tugev
    0.07
    ायर
    0.07
    Activations Density 0.000%

    No Known Activations