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. 58930
    Prev
    Next
    INDEX
    Explanations

    talking or saying

    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
     राय
    -0.08
     ہونے
    -0.07
     необ
    -0.07
    ométr
    -0.07
    submit
    -0.07
     Perspectives
    -0.07
    دة
    -0.07
    お
    -0.07
    ivities
    -0.07
    Therefore
    -0.07
    POSITIVE LOGITS
     assertions
    0.09
     לעצ
    0.09
    召
    0.09
     affirmation
    0.08
     dismissal
    0.08
     scripture
    0.08
    reth
    0.08
     summons
    0.08
    atshe
    0.08
     summon
    0.08
    Activations Density 0.025%

    No Known Activations