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. 44166
    Prev
    Next
    INDEX
    Explanations

    key

    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
     Foam
    -0.09
     volume
    -0.09
    	settings
    -0.09
    oppy
    -0.08
     Volume
    -0.08
    volume
    -0.08
    .Volume
    -0.08
     VBox
    -0.08
     volumes
    -0.08
     CDs
    -0.08
    POSITIVE LOGITS
    _offsets
    0.09
    pairs
    0.09
    మీ
    0.09
    vaises
    0.08
     menschen
    0.08
     wewe
    0.08
    _pairs
    0.08
    ンタ
    0.08
    Public
    0.08
    points
    0.08
    Activations Density 0.002%

    No Known Activations