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. 112222
    Prev
    Next
    INDEX
    Explanations

    but

    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
    spaper
    -0.09
     stuff
    -0.08
    ๆ
    -0.08
     olds
    -0.07
    Stuff
    -0.07
     paramount
    -0.07
    มัน
    -0.07
     moviment
    -0.07
    ствен
    -0.07
    clazz
    -0.07
    POSITIVE LOGITS
     unable
    0.13
    无法
    0.12
     नहीं
    0.09
     قادر
    0.09
     belum
    0.09
     Unable
    0.09
     couldn't
    0.09
     नहि
    0.09
     نہیں
    0.09
     unless
    0.08
    Activations Density 0.015%

    No Known Activations