Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60614
    Prev
    Next
    INDEX
    Explanations

    unreal

    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
     Hj
    -0.09
     doucement
    -0.08
     amic
    -0.08
     dlou
    -0.08
     ajili
    -0.08
     ташкил
    -0.08
     kipindi
    -0.07
     Haarlem
    -0.07
     પ્રથમ
    -0.07
    ngwe
    -0.07
    POSITIVE LOGITS
     Hollywood
    0.07
     physics
    0.07
    .Remove
    0.07
    actively
    0.07
    cu
    0.07
     collagen
    0.07
    compiler
    0.07
    cg
    0.07
    年前
    0.07
    .math
    0.07
    Activations Density 0.003%

    No Known Activations