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. 462
    Prev
    Next
    INDEX
    Explanations

    Punctuation and conjunctions

    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
    .ind
    -0.08
    mq
    -0.08
    াক্ত
    -0.07
    Rob
    -0.07
    Seleccion
    -0.07
    Prec
    -0.07
    kx
    -0.07
    ifies
    -0.07
    redu
    -0.07
    passen
    -0.07
    POSITIVE LOGITS
     Yay
    0.08
    	win
    0.08
     투
    0.08
    ിന്
    0.08
     بج
    0.08
     Zwolle
    0.08
    	      
    0.07
     Cer
    0.07
    	login
    0.07
    ાહી
    0.07
    Activations Density 0.404%

    No Known Activations