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. 30701
    Prev
    Next
    INDEX
    Explanations

    Bringing things from outside

    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
     forming
    -0.09
    ൈന
    -0.08
    ार
    -0.07
    推进
    -0.07
    ование
    -0.07
     staking
    -0.07
    ાઇન
    -0.07
    فاء
    -0.07
     both
    -0.07
     redund
    -0.07
    POSITIVE LOGITS
    回来
    0.12
    戻
    0.11
     freshly
    0.11
     regreso
    0.11
     hasil
    0.10
     возвращ
    0.10
     berasal
    0.10
     afkomstig
    0.10
     frisch
    0.10
     pós
    0.09
    Activations Density 0.104%

    No Known Activations