Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60608
    Prev
    Next
    INDEX
    Explanations

    Agreement/Affirmation

    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
    itura
    -0.08
    幅
    -0.07
     рейтин
    -0.07
    评级
    -0.07
     nime
    -0.07
     motto
    -0.07
    入口
    -0.07
     যথ
    -0.07
    illa
    -0.07
     sukk
    -0.07
    POSITIVE LOGITS
     tortor
    0.09
     Jorn
    0.08
     unglaublich
    0.08
     PROFESS
    0.08
    čnost
    0.08
    DAR
    0.08
     보여
    0.08
     delir
    0.08
    ,data
    0.08
    feed
    0.08
    Activations Density 0.015%

    No Known Activations