Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98409
    Prev
    Next
    INDEX
    Explanations

    Say "presumably"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Might
    -0.15
    might
    -0.13
     might
    -0.13
     pourraient
    -0.13
     könnten
    -0.12
     Could
    -0.12
     may
    -0.11
     could
    -0.11
    could
    -0.11
    may
    -0.11
    POSITIVE LOGITS
     I
    0.33
     essentially
    0.27
    I
    0.27
     typically
    0.27
     basically
    0.26
     presumably
    0.23
    	I
    0.22
     generalmente
    0.22
    typically
    0.21
     généralement
    0.21
    Activations Density 0.668%

    No Known Activations