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. 109312
    Prev
    Next
    INDEX
    Explanations

    B Corp

    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
     samengesteld
    -0.07
     Guth
    -0.07
     keinen
    -0.07
     senza
    -0.07
    ḥ
    -0.07
    adecimal
    -0.07
    subscriptions
    -0.07
     Eric
    -0.07
     flats
    -0.07
    _DURATION
    -0.07
    POSITIVE LOGITS
     sauv
    0.08
     био
    0.08
     biomechanics
    0.08
     ambition
    0.08
     ಉದ್ಯ
    0.08
     ગણ
    0.08
    になる
    0.07
     nonprofits
    0.07
     athletics
    0.07
     biome
    0.07
    Activations Density 0.001%

    No Known Activations