© 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. 19-RESID-POST-AA
    11. 102168
    Prev
    Next
    INDEX
    Explanations

    say comma

    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
    즌
    -0.09
    maktadır
    -0.09
    हरूले
    -0.08
     Potential
    -0.08
    Yak
    -0.08
    가능
    -0.08
    ajt
    -0.08
    adır
    -0.08
     Brass
    -0.08
    드립니다
    -0.08
    POSITIVE LOGITS
     commas
    0.15
     comma
    0.14
     punctuation
    0.13
    comma
    0.12
    unctuation
    0.12
     newline
    0.11
     whitespace
    0.11
     ','
    0.11
    Comma
    0.10
    semicolon
    0.10
    Activations Density 0.000%

    No Known Activations