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. 55672
    Prev
    Next
    INDEX
    Explanations

    red

    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
    .owl
    -0.08
     believer
    -0.08
     Validator
    -0.08
     assortment
    -0.08
     □
    -0.07
     communicator
    -0.07
     ord
    -0.07
     VAL
    -0.07
     bula
    -0.07
     enthält
    -0.07
    POSITIVE LOGITS
     alternating
    0.08
     costes
    0.08
    六月
    0.07
     dvoj
    0.07
     гор
    0.07
    成本
    0.07
    最大的
    0.07
     inher
    0.07
    哭
    0.07
    類
    0.07
    Activations Density 0.001%

    No Known Activations