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. 48873
    Prev
    Next
    INDEX
    Explanations

    's

    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
    หลัง
    -0.08
     missile
    -0.08
    <th
    -0.08
     pasada
    -0.07
     addresses
    -0.07
     δί
    -0.07
            		
    -0.07
    ентар
    -0.07
     mysql
    -0.07
     précédente
    -0.07
    POSITIVE LOGITS
    str
    0.08
    _busy
    0.08
     seu
    0.08
     Judah
    0.08
     Veg
    0.08
    nije
    0.08
    Busy
    0.08
     varit
    0.07
     Sant
    0.07
     Schule
    0.07
    Activations Density 0.000%

    No Known Activations