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. 8603
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    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
     locate
    -0.07
    /open
    -0.07
    cloak
    -0.07
    Locate
    -0.07
     Locale
    -0.07
    176
    -0.07
     tolerant
    -0.07
     segmentation
    -0.07
    navigation
    -0.07
    afka
    -0.07
    POSITIVE LOGITS
     заслуж
    0.09
     deserved
    0.08
    原创
    0.07
     trò
    0.07
     betr
    0.07
     mass
    0.07
     deserving
    0.07
     scripted
    0.07
    主持
    0.07
     materially
    0.07
    Activations Density 0.023%

    No Known Activations