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. 53179
    Prev
    Next
    INDEX
    Explanations

    Car controls

    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
     учен
    -0.09
     academically
    -0.08
     "\""
    -0.08
     selling
    -0.08
    理论
    -0.08
     explanatory
    -0.08
     '"'
    -0.08
     gin
    -0.08
     acad
    -0.08
    -0.08
    POSITIVE LOGITS
    Buttons
    0.10
    _buttons
    0.10
     buttons
    0.09
     deth
    0.09
     multifunction
    0.09
     клав
    0.09
    .BUTTON
    0.09
    	button
    0.09
    Notifications
    0.09
     नियन्त्रण
    0.08
    Activations Density 0.008%

    No Known Activations