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. 26967
    Prev
    Next
    INDEX
    Explanations

    sensational/unusual story titles

    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
     fraction
    -0.08
     drains
    -0.08
    .foundation
    -0.08
    pox
    -0.08
    _fraction
    -0.08
     жерде
    -0.08
    fraction
    -0.07
     cheiro
    -0.07
    .i
    -0.07
     Graves
    -0.07
    POSITIVE LOGITS
     제목
    0.23
    标题
    0.22
    タイトル
    0.21
     title
    0.20
     Titel
    0.19
     Title
    0.18
     titel
    0.18
     título
    0.18
     titled
    0.18
    	title
    0.17
    Activations Density 0.384%

    No Known Activations