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. 111640
    Prev
    Next
    INDEX
    Explanations

    review

    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
     tuple
    -0.08
    ="/">↵
    -0.07
    melon
    -0.07
    iki
    -0.07
     transcend
    -0.07
     COPY
    -0.07
     togg
    -0.07
    ίσ
    -0.07
    tuple
    -0.07
     embossed
    -0.07
    POSITIVE LOGITS
     littérature
    0.10
     ಸಾಹಿತ್ಯ
    0.10
     achtergrond
    0.09
     সাহিত্য
    0.09
     antecedentes
    0.09
     literatura
    0.09
     Literature
    0.09
     literature
    0.09
     cited
    0.09
     साहित्य
    0.09
    Activations Density 0.015%

    No Known Activations