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. 52939
    Prev
    Next
    INDEX
    Explanations

    over

    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
    Holder
    -0.08
     Kuk
    -0.08
    gga
    -0.08
    _holder
    -0.08
    бран
    -0.08
     Plasma
    -0.08
     plas
    -0.07
     HOLDER
    -0.07
    kai
    -0.07
     holder
    -0.07
    POSITIVE LOGITS
    'ouverture
    0.09
     ورود
    0.09
    ायला
    0.09
     آمد
    0.08
    (exception
    0.08
     unavoidable
    0.08
    'inscription
    0.08
     auftreten
    0.08
    (Exception
    0.08
     formidable
    0.08
    Activations Density 0.006%

    No Known Activations