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. 45011
    Prev
    Next
    INDEX
    Explanations

    sensitive

    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
     delegado
    -0.08
     Parl
    -0.08
    _COMP
    -0.08
     �
    -0.07
     dikenal
    -0.07
     xmax
    -0.07
     Margar
    -0.07
     affidavit
    -0.07
    ardır
    -0.07
     restorative
    -0.07
    POSITIVE LOGITS
    /raw
    0.08
     intact
    0.08
     strictly
    0.08
     distinctions
    0.08
     estrict
    0.08
     preserved
    0.08
    (password
    0.08
     Tilt
    0.08
     specificity
    0.08
    cipline
    0.08
    Activations Density 0.010%

    No Known Activations