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. 44071
    Prev
    Next
    INDEX
    Explanations

    'C

    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
    .rdb
    -0.08
    .issue
    -0.08
    期間
    -0.08
    మ
    -0.08
    యోగ
    -0.07
     Garn
    -0.07
     Granite
    -0.07
     Temporal
    -0.07
     underwriting
    -0.07
     Tal
    -0.07
    POSITIVE LOGITS
    eneration
    0.08
    cc
    0.07
     meat
    0.07
     flap
    0.07
     medi
    0.07
    odol
    0.07
    ��
    0.07
     foremost
    0.07
    Root
    0.07
    ib
    0.07
    Activations Density 0.004%

    No Known Activations