© 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. 48638
    Prev
    Next
    INDEX
    Explanations

    Chemistry terms

    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
    AC
    -0.08
     Faces
    -0.07
    Faces
    -0.07
     BST
    -0.07
    _FS
    -0.07
     planet
    -0.07
    .Objects
    -0.07
    ീസ
    -0.07
     tercer
    -0.07
     third
    -0.07
    POSITIVE LOGITS
    io
    0.13
    iod
    0.12
    ione
    0.11
    ina
    0.11
    ioq
    0.11
    jonijiet
    0.10
    iov
    0.10
    .io
    0.10
    ioc
    0.10
    iog
    0.10
    Activations Density 0.001%

    No Known Activations