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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27338
    Prev
    Next
    INDEX
    Explanations

    Biblical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ех
    -0.07
    Part
    -0.07
    Therefore
    -0.07
    L
    -0.07
    Note
    -0.07
    BOARD
    -0.07
    Label
    -0.07
    Natürlich
    -0.07
    альность
    -0.07
    ạy
    -0.07
    POSITIVE LOGITS
     usu
    0.09
     sept
    0.08
     quar
    0.08
    _ax
    0.08
     Crushers
    0.08
     Republic
    0.08
    ോക
    0.07
     Axel
    0.07
    _AX
    0.07
     Vas
    0.07
    Activations Density 0.001%

    No Known Activations