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. 8592
    Prev
    Next
    INDEX
    Explanations

    deficit

    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
     Douglas
    -0.09
    lief
    -0.07
    kins
    -0.07
     зан
    -0.07
    BAB
    -0.07
     Dennis
    -0.07
    Douglas
    -0.07
     xét
    -0.07
    bras
    -0.07
    kin
    -0.07
    POSITIVE LOGITS
     شف
    0.08
     التط
    0.07
    journal
    0.07
     قلي
    0.07
    ले
    0.07
     LE
    0.07
    .pub
    0.07
    CTOR
    0.07
     تمام
    0.07
    لے
    0.07
    Activations Density 0.002%

    No Known Activations