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. 67480
    Prev
    Next
    INDEX
    Explanations

    rock, stone

    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
     (+
    -0.08
     boutiques
    -0.08
     vif
    -0.08
     provo
    -0.08
     unic
    -0.08
     suk
    -0.08
     throttle
    -0.07
    regeling
    -0.07
    omitempty
    -0.07
     Waist
    -0.07
    POSITIVE LOGITS
    岩
    0.15
    石
    0.13
     geological
    0.12
     geology
    0.12
    �
    0.11
     الصخور
    0.11
     stones
    0.11
     granite
    0.11
    矿
    0.11
     rocks
    0.11
    Activations Density 0.064%

    No Known Activations