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. 26822
    Prev
    Next
    INDEX
    Explanations

    Text analysis breakdown

    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
    attern
    -0.08
     agile
    -0.08
     innovative
    -0.07
     vase
    -0.07
     diversity
    -0.07
    /div
    -0.07
     expedited
    -0.07
    łada
    -0.07
    upr
    -0.07
     Davenport
    -0.07
    POSITIVE LOGITS
    ុំ
    0.08
     individuel
    0.08
     individuais
    0.08
     individually
    0.08
     individual
    0.08
     hiahia
    0.08
     жы
    0.08
     salaire
    0.08
     sentent
    0.08
     scoring
    0.07
    Activations Density 0.004%

    No Known Activations