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. 42493
    Prev
    Next
    INDEX
    Explanations

    -

    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
     Darm
    -0.08
     drainage
    -0.08
    ಲ್ಲಿ
    -0.07
     manner
    -0.07
    acters
    -0.07
     geri
    -0.07
     agitation
    -0.07
     níl
    -0.07
     Deng
    -0.07
    -0.07
    POSITIVE LOGITS
    essary
    0.10
    herlands
    0.09
    anmoins
    0.09
    ATIVE
    0.09
    ‍കിയ
    0.08
    rition
    0.08
     bật
    0.08
    uyen
    0.08
    Born
    0.08
    ‍കി
    0.08
    Activations Density 0.461%

    No Known Activations