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. 29796
    Prev
    Next
    INDEX
    Explanations

    mer

    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
    玉
    -0.08
     số
    -0.08
    老板
    -0.08
     kik
    -0.07
    狗
    -0.07
     Kell
    -0.07
     kren
    -0.07
    .ball
    -0.07
    .ce
    -0.07
     cerim
    -0.07
    POSITIVE LOGITS
     Wenger
    0.08
     (
    0.07
    <|endoftext|>
    0.07
    ABLE
    0.07
     Episodes
    0.07
    abli
    0.07
    ینه
    0.06
    ilised
    0.06
    International
    0.06
    Regions
    0.06
    Activations Density 0.703%

    No Known Activations