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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 97989
    Prev
    Next
    INDEX
    Explanations

    arm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nemen
    -0.10
    меж
    -0.10
    nega
    -0.09
     acos
    -0.08
    hout
    -0.08
     ukrain
    -0.08
    vő
    -0.08
    roat
    -0.08
    nachten
    -0.08
    kou
    -0.08
    POSITIVE LOGITS
    ament
    0.11
    aments
    0.11
    orer
    0.10
    ory
    0.10
    ada
    0.09
    urerie
    0.09
    ors
    0.09
    iger
    0.08
    adas
    0.08
    $order
    0.08
    Activations Density 0.001%

    No Known Activations