© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96930
    Prev
    Next
    INDEX
    Explanations

    ania

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригин
    -0.08
     request
    -0.08
    աբ
    -0.08
     мя
    -0.08
    ovy
    -0.08
    атов
    -0.08
     llam
    -0.08
     belly
    -0.08
     otc
    -0.08
    �
    -0.08
    POSITIVE LOGITS
    ania
    0.17
    ując
    0.16
    ujących
    0.16
    ują
    0.16
    ujące
    0.14
    aniu
    0.14
    aniem
    0.13
    uje
    0.13
    ujemy
    0.12
    anie
    0.12
    Activations Density 0.002%

    No Known Activations