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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98094
    Prev
    Next
    INDEX
    Explanations

    Network connection states

    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
     empfohlen
    -0.09
     aanbevolen
    -0.09
     TÜ
    -0.08
     näht
    -0.08
     venit
    -0.08
    critic
    -0.08
     recomienda
    -0.08
    recommended
    -0.08
     halls
    -0.08
     san
    -0.08
    POSITIVE LOGITS
    _RDWR
    0.11
    _NON
    0.10
    _SYNC
    0.10
    _ACK
    0.10
    _PASS
    0.10
    Established
    0.09
    _C
    0.09
     established
    0.09
    ACK
    0.09
    Connected
    0.09
    Activations Density 0.001%

    No Known Activations