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. 88017
    Prev
    Next
    INDEX
    Explanations

    animal and plant descriptions

    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
     aff
    -0.08
    Jess
    -0.08
    Different
    -0.08
     transcript
    -0.08
    _case
    -0.08
    eling
    -0.07
     sais
    -0.07
     uff
    -0.07
    issent
    -0.07
    ello
    -0.07
    POSITIVE LOGITS
     niches
    0.09
     habitats
    0.09
     fits
    0.09
     Habitat
    0.09
     wherever
    0.08
     ويت
    0.08
     dij
    0.08
    ،
    0.08
     habitat
    0.08
     conditions
    0.08
    Activations Density 0.071%

    No Known Activations