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. 59371
    Prev
    Next
    INDEX
    Explanations

    photography

    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
     zusamment
    -0.09
    laš
    -0.08
    Iter
    -0.08
     समित
    -0.08
     estat
    -0.08
     клад
    -0.07
     endereço
    -0.07
     парламент
    -0.07
    elate
    -0.07
    lbl
    -0.07
    POSITIVE LOGITS
     glossy
    0.10
    肌
    0.09
     creamy
    0.09
     flattering
    0.09
    луб
    0.09
     mik
    0.09
     rejecting
    0.09
     تأثير
    0.08
    �
    0.08
     artists
    0.08
    Activations Density 0.016%

    No Known Activations