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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12141
    Prev
    Next
    INDEX
    Explanations

    single digit numbers

    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
     RAC
    -0.10
     COB
    -0.09
     pew
    -0.08
    Gren
    -0.08
     hingegen
    -0.08
     जै
    -0.08
     jen
    -0.08
     určit
    -0.08
     ACCOUNT
    -0.07
     HOM
    -0.07
    POSITIVE LOGITS
    列
    0.09
    -et
    0.08
     listing
    0.08
    iliar
    0.08
    _et
    0.08
    iliary
    0.07
    ivin
    0.07
    leet
    0.07
    lijst
    0.07
    usy
    0.07
    Activations Density 0.003%

    No Known Activations