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. 45005
    Prev
    Next
    INDEX
    Explanations

    bouncing balls

    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
    Trusted
    -0.08
    Nec
    -0.08
     personalized
    -0.08
     Personalized
    -0.08
    يًا
    -0.07
     personalised
    -0.07
    .portlet
    -0.07
    Absolute
    -0.07
     Oval
    -0.07
     Alph
    -0.07
    POSITIVE LOGITS
    nth
    0.11
    Nth
    0.11
     alternating
    0.11
     nth
    0.10
     altern
    0.09
    sequence
    0.09
    _series
    0.09
    series
    0.09
     серии
    0.09
     series
    0.09
    Activations Density 0.012%

    No Known Activations