© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54848
    Prev
    Next
    INDEX
    Explanations

    CSS pseudo-classes

    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
     boodschap
    -0.09
     assimilation
    -0.09
     السف
    -0.08
    Exponent
    -0.08
     Christchurch
    -0.08
     assimil
    -0.08
     resurf
    -0.08
    沟
    -0.08
     verhaal
    -0.08
    .communication
    -0.08
    POSITIVE LOGITS
     "*"
    0.08
     féminin
    0.08
     &:
    0.08
     $("
    0.08
     sibling
    0.08
     modifiers
    0.08
     $('
    0.08
    selector
    0.08
     Firefox
    0.08
     (::
    0.08
    Activations Density 0.004%

    No Known Activations