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. 65303
    Prev
    Next
    INDEX
    Explanations

    geometry 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
    ூ
    -0.08
    か
    -0.08
     snail
    -0.08
    蛇
    -0.08
     Presley
    -0.08
    িয়ে
    -0.08
    _AG
    -0.07
    Tel
    -0.07
    ேய
    -0.07
    COL
    -0.07
    POSITIVE LOGITS
     impuls
    0.08
     guider
    0.08
     ciudad
    0.08
     �
    0.08
    =(
    0.08
     trägt
    0.08
     أر
    0.07
     هد
    0.07
    =<
    0.07
    rump
    0.07
    Activations Density 0.038%

    No Known Activations