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. 9201
    Prev
    Next
    INDEX
    Explanations

    parenthesis

    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
     clin
    -0.08
     entire
    -0.08
     seren
    -0.08
     parametr
    -0.07
    iau
    -0.07
    *_
    -0.07
      
    -0.07
     gesam
    -0.07
     references
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Tend
    0.09
    (!(
    0.08
    נ
    0.08
     кажется
    0.08
    yyvsp
    0.08
     пом
    0.08
     ((*
    0.08
     (!(
    0.08
     о
    0.07
     CPF
    0.07
    Activations Density 0.007%

    No Known Activations