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. 102938
    Prev
    Next
    INDEX
    Explanations

    where which

    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
    obile
    -0.09
    idhi
    -0.08
    q
    -0.08
    	C
    -0.08
     Alley
    -0.08
    /url
    -0.08
     dager
    -0.08
     arah
    -0.07
     cuanto
    -0.07
    	t
    -0.07
    POSITIVE LOGITS
     vandaan
    0.10
     આવેલા
    0.10
     অনুষ্ঠিত
    0.09
    0.09
     stattfinden
    0.09
     upbringing
    0.09
     проживания
    0.08
     રહે
    0.08
     આવેલી
    0.08
    举办
    0.08
    Activations Density 0.072%

    No Known Activations