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. 77148
    Prev
    Next
    INDEX
    Explanations

    Let's

    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
     harmful
    -0.09
    түр
    -0.09
     fined
    -0.09
     સ્ત
    -0.08
     fréquent
    -0.08
     магаз
    -0.08
    Costo
    -0.08
     voorkomen
    -0.08
     Sympathy
    -0.08
     штраф
    -0.08
    POSITIVE LOGITS
     gemeinsam
    0.13
     enthusiasm
    0.12
     teamwork
    0.12
     enthousiasme
    0.12
     embarking
    0.11
     collaboratively
    0.11
     kickoff
    0.11
     collaborating
    0.11
     enthusiast
    0.11
     కలిసి
    0.11
    Activations Density 0.018%

    No Known Activations