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. 7-RESID-POST-AA
    6. 1717
    Prev
    Next
    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    톤
    -0.08
     udara
    -0.08
    secondary
    -0.08
     visas
    -0.07
     vacancies
    -0.07
    '.$
    -0.07
     Thumb
    -0.07
    -0.07
     воздуха
    -0.07
     infar
    -0.07
    POSITIVE LOGITS
     lied
    0.09
     Ag
    0.08
     intimate
    0.08
     istic
    0.08
     deline
    0.08
    ہم
    0.07
     Hosting
    0.07
     今日
    0.07
     ntx
    0.07
     участв
    0.07
    Activations Density 0.004%

    No Known Activations