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. 106057
    Prev
    Next
    INDEX
    Explanations

    two

    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
    ити
    -0.08
     מאוד
    -0.08
     Silva
    -0.08
    -dose
    -0.07
     przestr
    -0.07
    inarily
    -0.07
     במיוחד
    -0.07
    onet
    -0.07
     prób
    -0.07
     തുടങ്ങി
    -0.07
    POSITIVE LOGITS
     hype
    0.08
     descript
    0.07
    ್ಕೆ
    0.07
     relic
    0.07
     cuesta
    0.07
     unicorn
    0.07
     Colour
    0.07
     Apart
    0.07
    AVAILABLE
    0.07
     septiembre
    0.07
    Activations Density 0.028%

    No Known Activations