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. 12594
    Prev
    Next
    INDEX
    Explanations

    noble gases

    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
     cheap
    -0.09
     जित
    -0.08
    भारत
    -0.08
    _ANDROID
    -0.08
    Availability
    -0.08
    AMPL
    -0.08
     großzüg
    -0.08
     disponibilité
    -0.08
     loyalty
    -0.08
    “一带一路
    -0.08
    POSITIVE LOGITS
     Casper
    0.09
     Julius
    0.09
     FOX
    0.09
     Cmd
    0.08
     lineup
    0.08
    daan
    0.07
     havi
    0.07
     Lexer
    0.07
     Benn
    0.07
     Lenn
    0.07
    Activations Density 0.002%

    No Known Activations