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. 12279
    Prev
    Next
    INDEX
    Explanations

    RPM

    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
    xia
    -0.09
     phẩm
    -0.08
    represented
    -0.08
     embodied
    -0.07
     höf
    -0.07
     surpr
    -0.07
    xu
    -0.07
     funds
    -0.07
     иг
    -0.07
     Lydia
    -0.07
    POSITIVE LOGITS
    GHz
    0.09
     GHz
    0.09
     rpm
    0.09
    (theta
    0.09
     glossy
    0.08
    Hz
    0.08
    是多少
    0.08
     MHz
    0.08
     theta
    0.08
     boilers
    0.08
    Activations Density 0.005%

    No Known Activations