© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47914
    Prev
    Next
    INDEX
    Explanations

    letters "fl"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opioid
    -0.08
    enoid
    -0.08
    atee
    -0.08
     rojo
    -0.08
     opio
    -0.08
    inch
    -0.08
    opol
    -0.08
    xbet
    -0.08
    nable
    -0.08
    intend
    -0.08
    POSITIVE LOGITS
    utters
    0.13
     flutter
    0.11
    apping
    0.10
    itted
    0.10
    itting
    0.10
    apped
    0.09
    UT
    0.09
    APPED
    0.08
    ல்ல
    0.08
    飞
    0.08
    Activations Density 0.002%

    No Known Activations