Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19128
    Prev
    Next
    INDEX
    Explanations

    D

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spelled
    -0.10
    Erreur
    -0.09
     부분
    -0.08
     ચૂ
    -0.08
     sobren
    -0.08
    _setopt
    -0.08
    ਨ੍ਹਾਂ
    -0.08
    /error
    -0.08
    _this
    -0.08
     betekenen
    -0.08
    POSITIVE LOGITS
    imensional
    0.13
    rd
    0.09
    /M
    0.07
    ‑
    0.07
     rit
    0.07
     immersive
    0.07
     scans
    0.07
     stuff
    0.07
    /
    0.07
     Vision
    0.07
    Activations Density 0.016%

    No Known Activations