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. 49331
    Prev
    Next
    INDEX
    Explanations

    and

    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
     crumble
    -0.08
    olari
    -0.08
     pave
    -0.07
     mở
    -0.07
    —I
    -0.07
     mun
    -0.07
     Cold
    -0.07
     hanga
    -0.07
    _MATCH
    -0.07
    ಲೀ
    -0.07
    POSITIVE LOGITS
    season
    0.08
    0.08
     brit
    0.08
    ుకో
    0.07
     season
    0.07
    .Mode
    0.07
    istes
    0.07
    initions
    0.07
     unusually
    0.07
    ාන
    0.07
    Activations Density 0.012%

    No Known Activations