© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 206
    Prev
    Next
    INDEX
    Explanations

    Conditional statements

    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
     HGH
    -0.09
    .Hour
    -0.09
     Outra
    -0.08
    etet
    -0.08
     Rivera
    -0.08
     passend
    -0.08
     основу
    -0.08
     Obama's
    -0.08
     epiderm
    -0.08
     recib
    -0.08
    POSITIVE LOGITS
     isempty
    0.15
    isempty
    0.14
    Empty
    0.13
     empty
    0.13
     empt
    0.13
    (empty
    0.13
    .empty
    0.12
    _empty
    0.12
     emptied
    0.12
     Empty
    0.12
    Activations Density 0.004%

    No Known Activations