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. 49007
    Prev
    Next
    INDEX
    Explanations

    not

    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
     şəkildə
    -0.08
     guidance
    -0.08
     pourrez
    -0.07
    扣
    -0.07
     spoon
    -0.07
    യറ
    -0.07
    stijl
    -0.07
    ښ
    -0.07
     yesterday
    -0.07
    之后
    -0.07
    POSITIVE LOGITS
     Unknown
    0.10
     вообще
    0.09
     unknown
    0.09
     вовсе
    0.09
     совсем
    0.09
     desconhe
    0.08
    _UNKNOWN
    0.08
     неизвест
    0.08
     indef
    0.08
     None
    0.08
    Activations Density 0.015%

    No Known Activations