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. 30093
    Prev
    Next
    INDEX
    Explanations

    analysis

    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
     slider
    -0.08
     আদ
    -0.08
    驾驶
    -0.07
     土
    -0.07
     Sands
    -0.07
     pilote
    -0.07
    olph
    -0.07
     worldwide
    -0.07
     amad
    -0.07
     lookout
    -0.07
    POSITIVE LOGITS
    拆
    0.18
     decomposition
    0.15
     dissect
    0.15
     Breakdown
    0.13
     decom
    0.13
     separating
    0.13
     विभ
    0.13
     breakdown
    0.13
     dismant
    0.13
    Breaking
    0.12
    Activations Density 0.040%

    No Known Activations