Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43271
    Prev
    Next
    INDEX
    Explanations

    Tb

    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
    imana
    -0.08
     Store
    -0.08
    nění
    -0.07
     ontw
    -0.07
    }/>
    -0.07
     hasattr
    -0.07
    ingi
    -0.07
    _TOP
    -0.07
    liku
    -0.07
    avalu
    -0.07
    POSITIVE LOGITS
     tablespoons
    0.10
     tablespoon
    0.10
    scaled
    0.09
     convidados
    0.08
    Scaled
    0.08
     tbsp
    0.08
     comida
    0.08
     rope
    0.08
    Scaler
    0.08
     breakfast
    0.08
    Activations Density 0.005%

    No Known Activations