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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6284
    Prev
    Next
    INDEX
    Explanations

    say "numbers"

    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
     Circ
    -0.09
    Circ
    -0.08
    circ
    -0.08
    -prem
    -0.08
     côt
    -0.08
    兑
    -0.08
     തിര
    -0.07
    esseur
    -0.07
     Boutique
    -0.07
     circ
    -0.07
    POSITIVE LOGITS
    Profiler
    0.09
     meister
    0.08
    Mail
    0.08
    MAIL
    0.08
    /jpeg
    0.08
    GENER
    0.08
    ২০০
    0.08
    INVALID
    0.08
    _STARTED
    0.08
     masterpieces
    0.07
    Activations Density 0.000%

    No Known Activations