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. 60890
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
     बोल
    -0.08
     names
    -0.08
     जिसके
    -0.08
     rënd
    -0.07
     frontal
    -0.07
     pione
    -0.07
     पर
    -0.07
     Talking
    -0.07
     talking
    -0.07
    ランキング
    -0.07
    POSITIVE LOGITS
     voorbereiding
    0.08
     deducted
    0.08
     işlem
    0.08
     જાણવા
    0.08
    °C
    0.07
     ligi
    0.07
     restricted
    0.07
     Restricted
    0.07
     realized
    0.07
    Lights
    0.07
    Activations Density 0.068%

    No Known Activations