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. 114029
    Prev
    Next
    INDEX
    Explanations

    %

    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
    ISBN
    -0.10
     entry
    -0.08
     Kate
    -0.08
     isbn
    -0.07
    Refer
    -0.07
    imum
    -0.07
    URL
    -0.07
    ielte
    -0.07
    _main
    -0.07
     प्रवेश
    -0.07
    POSITIVE LOGITS
     moeite
    0.08
    +.
    0.08
     asym
    0.08
     сниж
    0.08
     श्रेष्ठ
    0.08
     võr
    0.08
     Verbesserung
    0.08
     ઘટાડ
    0.08
    %,
    0.08
     forbed
    0.08
    Activations Density 0.042%

    No Known Activations