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. 55135
    Prev
    Next
    INDEX
    Explanations

    cable

    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
     field
    -0.08
     inherent
    -0.07
     mathem
    -0.07
     brook
    -0.07
     transl
    -0.07
     äußerst
    -0.07
     Malawi
    -0.07
    caret
    -0.07
     cock
    -0.07
     caret
    -0.07
    POSITIVE LOGITS
     HBO
    0.09
     Genesis
    0.08
     Rox
    0.08
     टीवी
    0.08
     televisión
    0.08
    τέρα
    0.08
     toned
    0.08
    ordi
    0.08
    лиф
    0.08
     conven
    0.08
    Activations Density 0.011%

    No Known Activations