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. 55750
    Prev
    Next
    INDEX
    Explanations

    code and errors

    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
     compreh
    -0.08
    elis
    -0.08
    .entry
    -0.08
    ↵		↵
    -0.08
     invited
    -0.08
    整理
    -0.08
    Key
    -0.07
    Snapshot
    -0.07
     mods
    -0.07
    .export
    -0.07
    POSITIVE LOGITS
     действует
    0.08
    これは
    0.08
    	fl
    0.08
     sabemos
    0.08
     Speech
    0.08
     wahr
    0.08
     wav
    0.08
    ാണ
    0.08
     wagering
    0.08
     இது
    0.08
    Activations Density 0.001%

    No Known Activations