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. 30659
    Prev
    Next
    INDEX
    Explanations

    charge

    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
     inaug
    -0.09
     clauses
    -0.08
     Coimbra
    -0.08
    حد
    -0.08
     Luz
    -0.08
     يونيو
    -0.08
     inauguration
    -0.08
    Opened
    -0.07
    .inc
    -0.07
     совершен
    -0.07
    POSITIVE LOGITS
     negatively
    0.12
     acidic
    0.11
     neutrality
    0.11
     acidity
    0.10
     polarity
    0.10
     charges
    0.10
     positively
    0.10
     negatif
    0.10
     Charges
    0.09
    _negative
    0.09
    Activations Density 0.006%

    No Known Activations