© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47350
    Prev
    Next
    INDEX
    Explanations

    time references with "12"

    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
    Grammar
    -0.10
     договора
    -0.09
    Debt
    -0.09
    antlr
    -0.09
    Coords
    -0.09
    CGPoint
    -0.09
    Coin
    -0.09
    YGON
    -0.09
    证券
    -0.09
    }px
    -0.08
    POSITIVE LOGITS
    (hours
    0.15
     hours
    0.15
     overnight
    0.15
    _hours
    0.14
     घंटे
    0.14
    -hour
    0.13
    -hours
    0.13
    hours
    0.13
     Hours
    0.13
     morning
    0.13
    Activations Density 0.082%

    No Known Activations