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. 11587
    Prev
    Next
    INDEX
    Explanations

    risk and uncertainty

    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
    .S
    -0.09
    .Max
    -0.08
    	statement
    -0.07
    防
    -0.07
    .Al
    -0.07
    ikhail
    -0.07
    .Depth
    -0.07
    Max
    -0.07
    .lang
    -0.07
     permanently
    -0.07
    POSITIVE LOGITS
    తెల
    0.09
     xt
    0.09
    =<?
    0.08
     inconn
    0.08
     celestial
    0.08
     uncertain
    0.08
     elusive
    0.08
     emoties
    0.08
     vorhand
    0.08
     daneben
    0.08
    Activations Density 0.005%

    No Known Activations