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. 76470
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     storms
    -0.08
     نبود
    -0.08
     consideração
    -0.07
     foreseeable
    -0.07
     होइन
    -0.07
     consideración
    -0.07
     preocupação
    -0.07
     چاہیے
    -0.07
     Comp
    -0.07
     debería
    -0.07
    POSITIVE LOGITS
     Kyr
    0.08
    LOGGER
    0.08
    BERS
    0.07
    innamon
    0.07
    perl
    0.07
    NE
    0.07
     longitudinal
    0.07
     som
    0.07
     kaj
    0.07
     Body
    0.07
    Activations Density 0.000%

    No Known Activations