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. 74785
    Prev
    Next
    INDEX
    Explanations

    or

    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
     ure
    -0.08
     proti
    -0.08
     سول
    -0.07
     uranium
    -0.07
     treating
    -0.07
    usehen
    -0.07
    дай
    -0.07
     jäl
    -0.07
     deterministic
    -0.07
     Utah
    -0.07
    POSITIVE LOGITS
     tasteful
    0.10
    形式
    0.08
     condemnation
    0.08
     literary
    0.08
    �
    0.08
    Words
    0.08
    618
    0.08
    ocity
    0.08
     verbally
    0.08
    Invocation
    0.07
    Activations Density 0.021%

    No Known Activations