© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103317
    Prev
    Next
    INDEX
    Explanations

    power

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Names
    -0.09
     situació
    -0.08
     Glyph
    -0.08
     IGN
    -0.08
    quilla
    -0.08
     niño
    -0.08
     anuncio
    -0.08
     lijst
    -0.08
    名单
    -0.08
     सूची
    -0.08
    POSITIVE LOGITS
     power
    0.29
     powers
    0.29
    powers
    0.26
    power
    0.26
    _power
    0.25
    -power
    0.25
    Power
    0.24
     puissance
    0.23
    .power
    0.22
    (power
    0.22
    Activations Density 0.011%

    No Known Activations