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. 76353
    Prev
    Next
    INDEX
    Explanations

    programming

    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
     Sig
    -0.08
    Sig
    -0.08
    .sql
    -0.07
     Sep
    -0.07
     letter
    -0.07
     sig
    -0.07
     demanding
    -0.07
     tex
    -0.07
     Ce
    -0.06
    .libs
    -0.06
    POSITIVE LOGITS
     purifier
    0.08
     faible
    0.08
     ออนไลน์
    0.08
    なお
    0.08
     possuir
    0.08
    turn
    0.08
    �
    0.08
     सभा
    0.08
    therapy
    0.08
    otti
    0.08
    Activations Density 0.018%

    No Known Activations