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. 48356
    Prev
    Next
    INDEX
    Explanations

    spanning trees

    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
     coffee
    -0.08
     पाक
    -0.08
     listed
    -0.08
     �
    -0.07
     catcher
    -0.07
     heterosexual
    -0.07
     בק
    -0.07
     papi
    -0.07
     Pog
    -0.07
     космет
    -0.07
    POSITIVE LOGITS
    .minimum
    0.08
    ASTE
    0.08
    ুক
    0.08
     occupy
    0.08
     Yam
    0.08
    丰
    0.07
     pars
    0.07
     parcial
    0.07
    Discard
    0.07
     তৈ
    0.07
    Activations Density 0.002%

    No Known Activations