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. 61015
    Prev
    Next
    INDEX
    Explanations

    glimps

    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
    opin
    -0.08
    hp
    -0.07
     cis
    -0.07
    melon
    -0.07
    idad
    -0.07
    hv
    -0.07
     entram
    -0.07
    .arguments
    -0.07
     Said
    -0.07
     oz
    -0.07
    POSITIVE LOGITS
     glimpse
    0.12
     glimps
    0.10
     snag
    0.08
    ರ್ಶನ
    0.08
     Et
    0.08
    察
    0.08
    出来
    0.08
    ساء
    0.08
     Opportun
    0.08
     pr
    0.07
    Activations Density 0.006%

    No Known Activations