© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97752
    Prev
    Next
    INDEX
    Explanations

    R

    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
     ശ്ര
    -0.08
    JPEG
    -0.08
    nong
    -0.08
     refr
    -0.08
     curing
    -0.07
    BYTE
    -0.07
    Gam
    -0.07
    Rear
    -0.07
     будто
    -0.07
    释
    -0.07
    POSITIVE LOGITS
    ése
    0.11
    ê
    0.11
    année
    0.11
    émy
    0.10
    ên
    0.10
    enseign
    0.10
    ’aime
    0.10
    umeur
    0.09
    ive
    0.09
    omain
    0.09
    Activations Density 0.003%

    No Known Activations