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. 44187
    Prev
    Next
    INDEX
    Explanations

    well

    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
     एगो
    -0.08
     adjacency
    -0.08
     outfits
    -0.08
    �
    -0.08
    -her
    -0.08
     dij
    -0.08
     vowel
    -0.08
     condiment
    -0.08
     emot
    -0.07
     noticing
    -0.07
    POSITIVE LOGITS
     drilled
    0.13
     drilling
    0.12
     shafts
    0.10
    井
    0.09
     shaft
    0.09
    tube
    0.08
    Farm
    0.08
     bore
    0.08
     sunk
    0.08
     wells
    0.08
    Activations Density 0.011%

    No Known Activations