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. 44742
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
     Profiles
    -0.08
     upfront
    -0.08
    íveis
    -0.07
     mentors
    -0.07
     Nets
    -0.07
     thwart
    -0.07
     dramatically
    -0.07
     জানা
    -0.07
    挑战
    -0.07
     notorious
    -0.07
    POSITIVE LOGITS
     underside
    0.09
     rechtstreeks
    0.08
     има
    0.08
    .direct
    0.08
    esai
    0.08
     diap
    0.07
     bisan
    0.07
    <-
    0.07
    깨
    0.07
    에게
    0.07
    Activations Density 0.008%

    No Known Activations