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. 112453
    Prev
    Next
    INDEX
    Explanations

    膜

    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
     undertaken
    -0.08
    ುತ್ತಿರುವ
    -0.08
     proxies
    -0.08
    _tail
    -0.07
    För
    -0.07
     التصميم
    -0.07
     Lyme
    -0.07
     покаж
    -0.07
    ónico
    -0.07
    шие
    -0.07
    POSITIVE LOGITS
     flora
    0.09
     brave
    0.08
     sensibil
    0.08
     Kay
    0.08
     Randall
    0.08
    薄
    0.08
    -covered
    0.08
     Denis
    0.08
     tykk
    0.07
     FAR
    0.07
    Activations Density 0.004%

    No Known Activations