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. 12239
    Prev
    Next
    INDEX
    Explanations

    enforce

    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
     사고
    -0.08
     hingegen
    -0.08
    ikke
    -0.08
    hara
    -0.07
    مالك
    -0.07
     yüzden
    -0.07
     empf
    -0.07
     sincer
    -0.07
     Spread
    -0.07
    hap
    -0.07
    POSITIVE LOGITS
    able
    0.17
    যোগ্য
    0.17
    ABLE
    0.14
    ability
    0.14
    -able
    0.13
    izable
    0.13
    ably
    0.12
    atable
    0.12
    नीय
    0.12
    eworthy
    0.12
    Activations Density 0.048%

    No Known Activations