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. 117560
    Prev
    Next
    INDEX
    Explanations

    error

    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
     embodied
    -0.07
    ull
    -0.07
     lem
    -0.07
     incorporates
    -0.07
     cinemat
    -0.07
     ova
    -0.07
    attrs
    -0.07
    Callbacks
    -0.07
    staticmethod
    -0.07
     honom
    -0.07
    POSITIVE LOGITS
    ©
    0.09
    Ingrese
    0.08
     §
    0.08
     Moy
    0.08
    >This
    0.08
     ©
    0.08
    ('(
    0.08
    :"
    0.08
    ("(
    0.07
     Wid
    0.07
    Activations Density 0.013%

    No Known Activations