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. 15-RESID-POST-AA
    6. 19471
    Prev
    Next
    INDEX
    Explanations

    failure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     importancia
    -0.08
     utilizing
    -0.08
     importance
    -0.08
     đúng
    -0.07
    lunes
    -0.07
    ociated
    -0.07
     betrekking
    -0.07
     основных
    -0.07
     영향
    -0.07
     modifying
    -0.07
    POSITIVE LOGITS
    无法
    0.12
     understandably
    0.12
     refused
    0.12
     пыта
    0.11
     fails
    0.11
     رفض
    0.11
     helaas
    0.10
     refuses
    0.10
     can't
    0.10
     rejects
    0.10
    Activations Density 0.007%

    No Known Activations