© 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. 15-RESID-POST-AA
    11. 16477
    Prev
    Next
    INDEX
    Explanations

    out

    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
    ині
    -0.08
    synt
    -0.08
    mostly
    -0.07
     assigning
    -0.07
    esthetic
    -0.07
    _SY
    -0.07
    _WRITE
    -0.07
     Dif
    -0.07
    _CTL
    -0.07
    assigned
    -0.07
    POSITIVE LOGITS
     निकाल
    0.10
     оруж
    0.10
     extracts
    0.09
     substring
    0.09
     dévo
    0.09
    .tools
    0.08
     weapons
    0.08
     chứa
    0.08
     desple
    0.08
     나온
    0.08
    Activations Density 0.012%

    No Known Activations