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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52641
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ded
    -0.09
    thest
    -0.09
    -notch
    -0.08
    atch
    -0.08
    èles
    -0.08
     مرکزی
    -0.08
    -0.08
    щика
    -0.07
     Wrest
    -0.07
    -through
    -0.07
    POSITIVE LOGITS
     terminology
    0.24
     nomen
    0.22
     naming
    0.19
    Termin
    0.17
    名称
    0.17
     jargon
    0.17
    Naming
    0.16
     slang
    0.16
     phr
    0.16
     wording
    0.16
    Activations Density 0.170%

    No Known Activations