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. 101744
    Prev
    Next
    INDEX
    Explanations

    Lists of proper nouns

    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
     стороны
    -0.09
     supl
    -0.08
     konnte
    -0.08
    상의
    -0.08
    ңыз
    -0.08
     eji
    -0.07
    *)&
    -0.07
     puisse
    -0.07
     دارای
    -0.07
     edging
    -0.07
    POSITIVE LOGITS
    ™
    0.13
     II
    0.11
    ®
    0.10
     III
    0.10
     aka
    0.09
    III
    0.09
    ™,
    0.08
    to
    0.08
    ®,
    0.08
    など
    0.08
    Activations Density 0.336%

    No Known Activations