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. 65296
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Pá
    -0.08
     Weiter
    -0.08
     Caja
    -0.08
     Omb
    -0.07
     Mem
    -0.07
     Narc
    -0.07
     Inser
    -0.07
     Inspector
    -0.07
     inspector
    -0.07
    äp
    -0.07
    POSITIVE LOGITS
     sayesinde
    0.08
     tombe
    0.08
    leszt
    0.08
    ਨਾਂ
    0.08
    oloj
    0.07
     oye
    0.07
     работает
    0.07
    тердің
    0.07
    ्दा
    0.07
     avem
    0.07
    Activations Density 0.005%

    No Known Activations