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. 102884
    Prev
    Next
    INDEX
    Explanations

    parentheses/brackets

    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
    PLUS
    -0.08
    کل
    -0.08
    _CAN
    -0.08
     Huff
    -0.08
     دانلود
    -0.07
     Guerr
    -0.07
     presta
    -0.07
     Gis
    -0.07
    .pic
    -0.07
     CLE
    -0.07
    POSITIVE LOGITS
     presidential
    0.08
     již
    0.08
    별
    0.07
     пла
    0.07
    indows
    0.07
     выстав
    0.07
     opslag
    0.07
    175
    0.07
    旭
    0.07
    REAK
    0.07
    Activations Density 0.006%

    No Known Activations