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. 67556
    Prev
    Next
    INDEX
    Explanations

    dielectric permittivity

    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
     sturdy
    -0.08
     shovel
    -0.08
    Shuffle
    -0.08
     Vag
    -0.08
     conveyor
    -0.08
    -0.08
     wooden
    -0.07
    _join
    -0.07
     plantation
    -0.07
     Shuffle
    -0.07
    POSITIVE LOGITS
     dielectric
    0.12
     diel
    0.10
     இல
    0.09
     fluctu
    0.09
     fluctuate
    0.09
    .alibaba
    0.09
    خفاض
    0.09
    _TEMP
    0.08
    _TAB
    0.08
    逐
    0.08
    Activations Density 0.003%

    No Known Activations