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. 9015
    Prev
    Next
    INDEX
    Explanations

    are

    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
    িদের
    -0.07
    uidor
    -0.07
     atractivo
    -0.07
     condenado
    -0.07
     andando
    -0.07
    Tema
    -0.07
     =
    -0.07
     encima
    -0.07
    Toda
    -0.07
     nº
    -0.07
    POSITIVE LOGITS
     volunteer
    0.10
     paperwork
    0.09
    诀窍
    0.08
     prerequisites
    0.08
     prerequisite
    0.08
    ARAM
    0.08
    有哪些
    0.08
    ��
    0.08
     રીત
    0.08
     logistical
    0.08
    Activations Density 0.017%

    No Known Activations