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. 223
    Prev
    Next
    INDEX
    Explanations

    Jungian psychology

    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
     contention
    -0.08
     fluor
    -0.08
     estimating
    -0.08
    _HOST
    -0.08
    _precision
    -0.07
     činjen
    -0.07
     smarter
    -0.07
     వేస
    -0.07
    -side
    -0.07
     inaccuracies
    -0.07
    POSITIVE LOGITS
     arche
    0.13
     psyche
    0.11
     journeys
    0.11
     Arche
    0.10
     motifs
    0.10
     narratives
    0.10
    英雄
    0.10
     psychotherapy
    0.10
     evokes
    0.09
     rites
    0.09
    Activations Density 0.014%

    No Known Activations