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. 18939
    Prev
    Next
    INDEX
    Explanations

    adjacency

    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
     reaffirm
    -0.08
    /poly
    -0.08
    ikers
    -0.07
     UIGraphics
    -0.07
    .jsx
    -0.07
     rosas
    -0.07
    规范
    -0.07
    _U
    -0.07
    .scss
    -0.07
    (texture
    -0.07
    POSITIVE LOGITS
     adjacent
    0.15
     அருக
    0.13
     adjacency
    0.13
     neighboring
    0.12
     preceded
    0.12
     consecutive
    0.12
    Adjacent
    0.12
     contiguous
    0.12
     preced
    0.12
     consecut
    0.12
    Activations Density 0.015%

    No Known Activations