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. 41960
    Prev
    Next
    INDEX
    Explanations

    day

    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
    ixing
    -0.09
    cro
    -0.08
     Steve
    -0.08
    acency
    -0.07
    Nich
    -0.07
    Steve
    -0.07
    _blank
    -0.07
     Lumi
    -0.07
    neider
    -0.07
     Xu
    -0.07
    POSITIVE LOGITS
    ,从
    0.09
    时候
    0.08
     الأحيان
    0.08
    ,比如
    0.08
    发行
    0.07
     ज
    0.07
    sip
    0.07
    ,否则
    0.07
     Hopkins
    0.07
     PEG
    0.07
    Activations Density 0.198%

    No Known Activations